org.neuroph.nnet.comp.layer

Class FeatureMapLayer

java.lang.Object

org.neuroph.core.Layer

org.neuroph.nnet.comp.layer.FeatureMapLayer

All Implemented Interfaces:

java.io.Serializable, java.lang.Iterable<Neuron>

public class FeatureMapLayer
extends Layer

FeatureMapLayer Layer provides 2D layout of the neurons in layer. All the neurons are actually stored in one dimensional array in superclass. This type of layer is used as feature map for convolutional networks

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
FeatureMapLayer(Dimension2D dimensions, Dimension2D kernelDimension) Creates an empty 2D layer with specified dimensions and kernel
FeatureMapLayer(Dimension2D dimensions, NeuronProperties neuronProperties) Creates an empty 2D layer with specified dimensions
FeatureMapLayer(Dimension2D dimensions, NeuronProperties neuronProperties, Dimension2D kernelDimension) Creates 2D layer with specified dimensions, filled with neurons with specified properties

Method Summary

Modifier and Type	Method and Description
Dimension2D	getDimensions() Returns dimensions of this layer
int	getHeight() Returns height of this layer
Kernel	getKernel()
Neuron	getNeuronAt(int x, int y) Returns neuron at specified position in this layer
int	getWidth() Returns width of this layer

Methods inherited from class org.neuroph.core.Layer

addNeuron, addNeuron, calculate, getLabel, getNeuronAt, getNeurons, getNeuronsCount, getParentNetwork, indexOf, initializeWeights, isEmpty, iterator, removeAllNeurons, removeNeuron, removeNeuronAt, reset, setLabel, setNeuron, setParentNetwork

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface java.lang.Iterable

forEach, spliterator

Constructor Detail

FeatureMapLayer

public FeatureMapLayer(Dimension2D dimensions,
                       NeuronProperties neuronProperties)

Creates an empty 2D layer with specified dimensions

Parameters:

dimensions - layer dimensions (width and weight)

FeatureMapLayer

public FeatureMapLayer(Dimension2D dimensions,
                       Dimension2D kernelDimension)

Creates an empty 2D layer with specified dimensions and kernel

Parameters:

dimensions - layer dimensions (width and weight)

FeatureMapLayer

public FeatureMapLayer(Dimension2D dimensions,
                       NeuronProperties neuronProperties,
                       Dimension2D kernelDimension)

Creates 2D layer with specified dimensions, filled with neurons with specified properties

Parameters:

dimensions - layer dimensions

neuronProperties - neuron properties

Method Detail

getWidth

public int getWidth()

Returns width of this layer

Returns:

width of this layer

getHeight

public int getHeight()

Returns height of this layer

Returns:

height of this layer

getDimensions

public Dimension2D getDimensions()

Returns dimensions of this layer

Returns:

dimensions of this layer

getNeuronAt

public Neuron getNeuronAt(int x,
                          int y)

Returns neuron at specified position in this layer

Parameters:

x - neuron's x position

y - neuron's y position

Returns:

neuron at specified position in this layer

getKernel

public Kernel getKernel()